diff options
author | David S. Miller <davem@davemloft.net> | 2013-08-17 00:37:26 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2013-08-17 00:37:26 +0200 |
commit | 2ff1cf12c9fe70e75e600404e6a4274b19d293ed (patch) | |
tree | beafddac0a8098e3f07d2ec60e44a2a7d006e605 /net | |
parent | netlink: Eliminate kmalloc in netlink dump operation. (diff) | |
parent | Merge tag 'clk-fixes-for-linus' of git://git.linaro.org/people/mturquette/linux (diff) | |
download | linux-2ff1cf12c9fe70e75e600404e6a4274b19d293ed.tar.xz linux-2ff1cf12c9fe70e75e600404e6a4274b19d293ed.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Diffstat (limited to 'net')
37 files changed, 230 insertions, 79 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 4a78c4de9f20..6ee48aac776f 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -91,7 +91,12 @@ EXPORT_SYMBOL(__vlan_find_dev_deep); struct net_device *vlan_dev_real_dev(const struct net_device *dev) { - return vlan_dev_priv(dev)->real_dev; + struct net_device *ret = vlan_dev_priv(dev)->real_dev; + + while (is_vlan_dev(ret)) + ret = vlan_dev_priv(ret)->real_dev; + + return ret; } EXPORT_SYMBOL(vlan_dev_real_dev); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index e14531f1ce1c..264de88db320 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1529,6 +1529,8 @@ out: * in these cases, the skb is further handled by this function and * returns 1, otherwise it returns 0 and the caller shall further * process the skb. + * + * This call might reallocate skb data. */ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index f105219f4a4b..7614af31daff 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -508,6 +508,7 @@ out: return 0; } +/* this call might reallocate skb data */ static bool batadv_is_type_dhcprequest(struct sk_buff *skb, int header_len) { int ret = false; @@ -568,6 +569,7 @@ out: return ret; } +/* this call might reallocate skb data */ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) { struct ethhdr *ethhdr; @@ -619,6 +621,12 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr))) return false; + + /* skb->data might have been reallocated by pskb_may_pull() */ + ethhdr = (struct ethhdr *)skb->data; + if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) + ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN); + udphdr = (struct udphdr *)(skb->data + *header_len); *header_len += sizeof(*udphdr); @@ -634,12 +642,14 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) return true; } +/* this call might reallocate skb data */ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, - struct sk_buff *skb, struct ethhdr *ethhdr) + struct sk_buff *skb) { struct batadv_neigh_node *neigh_curr = NULL, *neigh_old = NULL; struct batadv_orig_node *orig_dst_node = NULL; struct batadv_gw_node *curr_gw = NULL; + struct ethhdr *ethhdr; bool ret, out_of_range = false; unsigned int header_len = 0; uint8_t curr_tq_avg; @@ -648,6 +658,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!ret) goto out; + ethhdr = (struct ethhdr *)skb->data; orig_dst_node = batadv_transtable_search(bat_priv, ethhdr->h_source, ethhdr->h_dest); if (!orig_dst_node) diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 039902dca4a6..1037d75da51f 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -34,7 +34,6 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv, void batadv_gw_node_purge(struct batadv_priv *bat_priv); int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset); bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len); -bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, - struct sk_buff *skb, struct ethhdr *ethhdr); +bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb); #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 700d0b49742d..0f04e1c302b4 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -180,6 +180,9 @@ static int batadv_interface_tx(struct sk_buff *skb, if (batadv_bla_tx(bat_priv, skb, vid)) goto dropped; + /* skb->data might have been reallocated by batadv_bla_tx() */ + ethhdr = (struct ethhdr *)skb->data; + /* Register the client MAC in the transtable */ if (!is_multicast_ether_addr(ethhdr->h_source)) batadv_tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); @@ -220,6 +223,10 @@ static int batadv_interface_tx(struct sk_buff *skb, default: break; } + + /* reminder: ethhdr might have become unusable from here on + * (batadv_gw_is_dhcp_target() might have reallocated skb data) + */ } /* ethernet packet should be broadcasted */ @@ -266,7 +273,7 @@ static int batadv_interface_tx(struct sk_buff *skb, /* unicast packet */ } else { if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_OFF) { - ret = batadv_gw_out_of_range(bat_priv, skb, ethhdr); + ret = batadv_gw_out_of_range(bat_priv, skb); if (ret) goto dropped; } diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index dc8b5d4dd636..688a0419756b 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -326,7 +326,9 @@ static bool batadv_unicast_push_and_fill_skb(struct sk_buff *skb, int hdr_size, * @skb: the skb containing the payload to encapsulate * @orig_node: the destination node * - * Returns false if the payload could not be encapsulated or true otherwise + * Returns false if the payload could not be encapsulated or true otherwise. + * + * This call might reallocate skb data. */ static bool batadv_unicast_prepare_skb(struct sk_buff *skb, struct batadv_orig_node *orig_node) @@ -343,7 +345,9 @@ static bool batadv_unicast_prepare_skb(struct sk_buff *skb, * @orig_node: the destination node * @packet_subtype: the batman 4addr packet subtype to use * - * Returns false if the payload could not be encapsulated or true otherwise + * Returns false if the payload could not be encapsulated or true otherwise. + * + * This call might reallocate skb data. */ bool batadv_unicast_4addr_prepare_skb(struct batadv_priv *bat_priv, struct sk_buff *skb, @@ -401,7 +405,7 @@ int batadv_unicast_generic_send_skb(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh_node; int data_len = skb->len; int ret = NET_RX_DROP; - unsigned int dev_mtu; + unsigned int dev_mtu, header_len; /* get routing information */ if (is_multicast_ether_addr(ethhdr->h_dest)) { @@ -429,10 +433,12 @@ find_router: switch (packet_type) { case BATADV_UNICAST: batadv_unicast_prepare_skb(skb, orig_node); + header_len = sizeof(struct batadv_unicast_packet); break; case BATADV_UNICAST_4ADDR: batadv_unicast_4addr_prepare_skb(bat_priv, skb, orig_node, packet_subtype); + header_len = sizeof(struct batadv_unicast_4addr_packet); break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It @@ -441,6 +447,7 @@ find_router: goto out; } + ethhdr = (struct ethhdr *)(skb->data + header_len); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 61c5e819380e..08e576ada0b2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1195,7 +1195,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); if (max_delay) group = &mld->mld_mca; - } else if (skb->len >= sizeof(*mld2q)) { + } else { if (!pskb_may_pull(skb, sizeof(*mld2q))) { err = -EINVAL; goto out; diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 394bb96b6087..3b9637fb7939 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -1,5 +1,5 @@ /* - * Sysfs attributes of bridge ports + * Sysfs attributes of bridge * Linux ethernet bridge * * Authors: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ade9ff1c1980..159737cac76c 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -65,6 +65,7 @@ ipv6: nhoff += sizeof(struct ipv6hdr); break; } + case __constant_htons(ETH_P_8021AD): case __constant_htons(ETH_P_8021Q): { const struct vlan_hdr *vlan; struct vlan_hdr _vlan; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 242084edb658..2a0e21de3060 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2179,7 +2179,7 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, /* If aging addresses are supported device will need to * implement its own handler for this. */ - if (ndm->ndm_state & NUD_PERMANENT) { + if (!(ndm->ndm_state & NUD_PERMANENT)) { pr_info("%s: FDB only supports static addresses\n", dev->name); return -EINVAL; } @@ -2407,7 +2407,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) struct nlattr *extfilt; u32 filter_mask = 0; - extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg), + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg), IFLA_EXT_MASK); if (extfilt) filter_mask = nla_get_u32(extfilt); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index ab3d814bc80a..109ee89f123e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -477,7 +477,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) } return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - - net_adj) & ~(align - 1)) + (net_adj - 2); + net_adj) & ~(align - 1)) + net_adj - 2; } static void esp4_err(struct sk_buff *skb, u32 info) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 108a1e9c9eac..3df6d3edb2a1 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -71,7 +71,6 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> -#include <linux/prefetch.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/ip.h> @@ -1761,10 +1760,8 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c) if (!c) continue; - if (IS_LEAF(c)) { - prefetch(rcu_dereference_rtnl(p->child[idx])); + if (IS_LEAF(c)) return (struct leaf *) c; - } /* Rescan start scanning in new node */ p = (struct tnode *) c; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index bc3a76521deb..d7aea4c5b940 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -383,7 +383,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) - return t->hlen; + return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 7167b08977df..850525b34899 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -76,9 +76,7 @@ int iptunnel_xmit(struct net *net, struct rtable *rt, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - tunnel_ip_select_ident(skb, - (const struct iphdr *)skb_inner_network_header(skb), - &rt->dst); + __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1); err = ip_local_out(skb); if (unlikely(net_xmit_eval(err))) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 5f5fa612647f..4a0335854b89 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -278,7 +278,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD), SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES), - SNMP_MIB_ITEM("LowLatencyRxPackets", LINUX_MIB_LOWLATENCYRXPACKETS), + SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index a9077f441cb2..b6ae92a51f58 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -206,8 +206,8 @@ static u32 cubic_root(u64 a) */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { - u64 offs; - u32 delta, t, bic_target, max_cnt; + u32 delta, bic_target, max_cnt; + u64 offs, t; ca->ack_cnt++; /* count the number of ACKs */ @@ -250,9 +250,11 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) * if the cwnd < 1 million packets !!! */ + t = (s32)(tcp_time_stamp - ca->epoch_start); + t += msecs_to_jiffies(ca->delay_min >> 3); /* change the unit from HZ to bictcp_HZ */ - t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3) - - ca->epoch_start) << BICTCP_HZ) / HZ; + t <<= BICTCP_HZ; + do_div(t, HZ); if (t < ca->bic_K) /* t - K */ offs = ca->bic_K - t; @@ -414,7 +416,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) return; /* Discard delay samples right after fast recovery */ - if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ) + if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ) return; delay = (rtt_us << 3) / USEC_PER_MSEC; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 40ffd72243a4..aeac0dc3635d 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -425,7 +425,7 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) net_adj = 0; return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - - net_adj) & ~(align - 1)) + (net_adj - 2); + net_adj) & ~(align - 1)) + net_adj - 2; } static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index ed828d6f37b2..73db48eba1c4 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -993,14 +993,22 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) - fn = fib6_lookup_1(fn->subtree, args + 1); + if (fn->subtree) { + struct fib6_node *sfn; + sfn = fib6_lookup_1(fn->subtree, + args + 1); + if (!sfn) + goto backtrack; + fn = sfn; + } #endif - if (!fn || fn->fn_flags & RTN_RTINFO) + if (fn->fn_flags & RTN_RTINFO) return fn; } } - +#ifdef CONFIG_IPV6_SUBTREES +backtrack: +#endif if (fn->fn_flags & RTN_ROOT) break; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 7dcc376eea5f..2f8010707d01 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -526,7 +526,7 @@ static bool tcp_in_window(const struct nf_conn *ct, const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; s16 receiver_offset; - bool res; + bool res, in_recv_win; /* * Get the required data from the packet. @@ -649,14 +649,18 @@ static bool tcp_in_window(const struct nf_conn *ct, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); + /* Is the ending sequence in the receive window (if available)? */ + in_recv_win = !receiver->td_maxwin || + after(end, sender->td_end - receiver->td_maxwin - 1); + pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n", before(seq, sender->td_maxend + 1), - after(end, sender->td_end - receiver->td_maxwin - 1), + (in_recv_win ? 1 : 0), before(sack, receiver->td_end + 1), after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)); if (before(seq, sender->td_maxend + 1) && - after(end, sender->td_end - receiver->td_maxwin - 1) && + in_recv_win && before(sack, receiver->td_end + 1) && after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) { /* @@ -725,7 +729,7 @@ static bool tcp_in_window(const struct nf_conn *ct, nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: %s ", before(seq, sender->td_maxend + 1) ? - after(end, sender->td_end - receiver->td_maxwin - 1) ? + in_recv_win ? before(sack, receiver->td_end + 1) ? after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG" : "ACK is under the lower bound (possible overly delayed ACK)" diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 962e9792e317..d92cc317bf8b 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -419,6 +419,7 @@ __build_packet_message(struct nfnl_log_net *log, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(inst->group_num); + memset(&pmsg, 0, sizeof(pmsg)); pmsg.hw_protocol = skb->protocol; pmsg.hook = hooknum; @@ -498,7 +499,10 @@ __build_packet_message(struct nfnl_log_net *log, if (indev && skb->dev && skb->mac_header != skb->network_header) { struct nfulnl_msg_packet_hw phw; - int len = dev_parse_header(skb, phw.hw_addr); + int len; + + memset(&phw, 0, sizeof(phw)); + len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { phw.hw_addrlen = htons(len); if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw)) diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 971ea145ab3e..8a703c3dd318 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -463,7 +463,10 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (indev && entskb->dev && entskb->mac_header != entskb->network_header) { struct nfqnl_msg_packet_hw phw; - int len = dev_parse_header(entskb, phw.hw_addr); + int len; + + memset(&phw, 0, sizeof(phw)); + len = dev_parse_header(entskb, phw.hw_addr); if (len) { phw.hw_addrlen = htons(len); if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw)) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 7011c71646f0..6113cc7efffc 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -52,7 +52,8 @@ tcpmss_mangle_packet(struct sk_buff *skb, { const struct xt_tcpmss_info *info = par->targinfo; struct tcphdr *tcph; - unsigned int tcplen, i; + int len, tcp_hdrlen; + unsigned int i; __be16 oldval; u16 newmss; u8 *opt; @@ -64,11 +65,14 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (!skb_make_writable(skb, skb->len)) return -1; - tcplen = skb->len - tcphoff; + len = skb->len - tcphoff; + if (len < (int)sizeof(struct tcphdr)) + return -1; + tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); + tcp_hdrlen = tcph->doff * 4; - /* Header cannot be larger than the packet */ - if (tcplen < tcph->doff*4) + if (len < tcp_hdrlen) return -1; if (info->mss == XT_TCPMSS_CLAMP_PMTU) { @@ -87,9 +91,8 @@ tcpmss_mangle_packet(struct sk_buff *skb, newmss = info->mss; opt = (u_int8_t *)tcph; - for (i = sizeof(struct tcphdr); i < tcph->doff*4; i += optlen(opt, i)) { - if (opt[i] == TCPOPT_MSS && tcph->doff*4 - i >= TCPOLEN_MSS && - opt[i+1] == TCPOLEN_MSS) { + for (i = sizeof(struct tcphdr); i <= tcp_hdrlen - TCPOLEN_MSS; i += optlen(opt, i)) { + if (opt[i] == TCPOPT_MSS && opt[i+1] == TCPOLEN_MSS) { u_int16_t oldmss; oldmss = (opt[i+2] << 8) | opt[i+3]; @@ -112,9 +115,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, } /* There is data after the header so the option can't be added - without moving it, and doing so may make the SYN packet - itself too large. Accept the packet unmodified instead. */ - if (tcplen > tcph->doff*4) + * without moving it, and doing so may make the SYN packet + * itself too large. Accept the packet unmodified instead. + */ + if (len > tcp_hdrlen) return 0; /* @@ -143,10 +147,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, newmss = min(newmss, (u16)1220); opt = (u_int8_t *)tcph + sizeof(struct tcphdr); - memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr)); + memmove(opt + TCPOLEN_MSS, opt, len - sizeof(struct tcphdr)); inet_proto_csum_replace2(&tcph->check, skb, - htons(tcplen), htons(tcplen + TCPOLEN_MSS), 1); + htons(len), htons(len + TCPOLEN_MSS), 1); opt[0] = TCPOPT_MSS; opt[1] = TCPOLEN_MSS; opt[2] = (newmss & 0xff00) >> 8; diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c index b68fa191710f..625fa1d636a0 100644 --- a/net/netfilter/xt_TCPOPTSTRIP.c +++ b/net/netfilter/xt_TCPOPTSTRIP.c @@ -38,7 +38,7 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, struct tcphdr *tcph; u_int16_t n, o; u_int8_t *opt; - int len; + int len, tcp_hdrlen; /* This is a fragment, no TCP header is available */ if (par->fragoff != 0) @@ -52,7 +52,9 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, return NF_DROP; tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); - if (tcph->doff * 4 > len) + tcp_hdrlen = tcph->doff * 4; + + if (len < tcp_hdrlen) return NF_DROP; opt = (u_int8_t *)tcph; @@ -61,10 +63,10 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, * Walk through all TCP options - if we find some option to remove, * set all octets to %TCPOPT_NOP and adjust checksum. */ - for (i = sizeof(struct tcphdr); i < tcp_hdrlen(skb); i += optl) { + for (i = sizeof(struct tcphdr); i < tcp_hdrlen - 1; i += optl) { optl = optlen(opt, i); - if (i + optl > tcp_hdrlen(skb)) + if (i + optl > tcp_hdrlen) break; if (!tcpoptstrip_test_bit(info->strip_bmap, opt[i])) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 512718adb0d5..f85f8a2ad6cf 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -789,6 +789,10 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); int chains_to_skip = cb->args[0]; int fams_to_skip = cb->args[1]; + bool need_locking = chains_to_skip || fams_to_skip; + + if (need_locking) + genl_lock(); for (i = chains_to_skip; i < GENL_FAM_TAB_SIZE; i++) { n = 0; @@ -810,6 +814,9 @@ errout: cb->args[0] = i; cb->args[1] = n; + if (need_locking) + genl_unlock(); + return skb->len; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 22c5f399f1cf..ab101f715447 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -535,6 +535,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb) { struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts); + OVS_CB(skb)->tun_key = NULL; return do_execute_actions(dp, skb, acts->actions, acts->actions_len, false); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f7e3a0d84c40..f2ed7600084e 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2076,9 +2076,6 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) ovs_notify(reply, info, &ovs_dp_vport_multicast_group); return 0; - rtnl_unlock(); - return 0; - exit_free: kfree_skb(reply); exit_unlock: diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 5c519b121e1b..1aa84dc58777 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -240,7 +240,7 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets) struct flex_array *buckets; int i, err; - buckets = flex_array_alloc(sizeof(struct hlist_head *), + buckets = flex_array_alloc(sizeof(struct hlist_head), n_buckets, GFP_KERNEL); if (!buckets) return NULL; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 281c1bded1f6..51b968d3febb 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -285,6 +285,45 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind) return q; } +/* The linklayer setting were not transferred from iproute2, in older + * versions, and the rate tables lookup systems have been dropped in + * the kernel. To keep backward compatible with older iproute2 tc + * utils, we detect the linklayer setting by detecting if the rate + * table were modified. + * + * For linklayer ATM table entries, the rate table will be aligned to + * 48 bytes, thus some table entries will contain the same value. The + * mpu (min packet unit) is also encoded into the old rate table, thus + * starting from the mpu, we find low and high table entries for + * mapping this cell. If these entries contain the same value, when + * the rate tables have been modified for linklayer ATM. + * + * This is done by rounding mpu to the nearest 48 bytes cell/entry, + * and then roundup to the next cell, calc the table entry one below, + * and compare. + */ +static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) +{ + int low = roundup(r->mpu, 48); + int high = roundup(low+1, 48); + int cell_low = low >> r->cell_log; + int cell_high = (high >> r->cell_log) - 1; + + /* rtab is too inaccurate at rates > 100Mbit/s */ + if ((r->rate > (100000000/8)) || (rtab[0] == 0)) { + pr_debug("TC linklayer: Giving up ATM detection\n"); + return TC_LINKLAYER_ETHERNET; + } + + if ((cell_high > cell_low) && (cell_high < 256) + && (rtab[cell_low] == rtab[cell_high])) { + pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n", + cell_low, cell_high, rtab[cell_high]); + return TC_LINKLAYER_ATM; + } + return TC_LINKLAYER_ETHERNET; +} + static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab) @@ -308,6 +347,8 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *ta rtab->rate = *r; rtab->refcnt = 1; memcpy(rtab->data, nla_data(tab), 1024); + if (r->linklayer == TC_LINKLAYER_UNAWARE) + r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 4626cef4b76e..48be3d5c0d92 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -25,6 +25,7 @@ #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/if_vlan.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> @@ -207,15 +208,19 @@ void __qdisc_run(struct Qdisc *q) unsigned long dev_trans_start(struct net_device *dev) { - unsigned long val, res = dev->trans_start; + unsigned long val, res; unsigned int i; + if (is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); + res = dev->trans_start; for (i = 0; i < dev->num_tx_queues; i++) { val = netdev_get_tx_queue(dev, i)->trans_start; if (val && time_after(val, res)) res = val; } dev->trans_start = res; + return res; } EXPORT_SYMBOL(dev_trans_start); @@ -904,6 +909,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; r->rate_bytes_ps = conf->rate; + r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); r->mult = 1; /* * The deal here is to replace a divide by a reciprocal one diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 45e751527dfc..c2178b15ca6e 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1329,6 +1329,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; + struct qdisc_rate_table *rtab = NULL, *ctab = NULL; struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_opt *hopt; @@ -1350,6 +1351,18 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!hopt->rate.rate || !hopt->ceil.rate) goto failure; + /* Keeping backward compatible with rate_table based iproute2 tc */ + if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) { + rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]); + if (rtab) + qdisc_put_rtab(rtab); + } + if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) { + ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]); + if (ctab) + qdisc_put_rtab(ctab); + } + if (!cl) { /* new class */ struct Qdisc *new_q; int prio; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index e051920816e6..cef509985192 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -840,12 +840,12 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, else spc_state = SCTP_ADDR_AVAILABLE; /* Don't inform ULP about transition from PF to - * active state and set cwnd to 1, see SCTP + * active state and set cwnd to 1 MTU, see SCTP * Quick failover draft section 5.1, point 5 */ if (transport->state == SCTP_PF) { ulp_notify = false; - transport->cwnd = 1; + transport->cwnd = asoc->pathmtu; } transport->state = SCTP_ACTIVE; break; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 6836ead5c957..e332efb124cc 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -175,12 +175,12 @@ static void sctp_transport_destroy(struct sctp_transport *transport) return; } - call_rcu(&transport->rcu, sctp_transport_destroy_rcu); - sctp_packet_free(&transport->packet); if (transport->asoc) sctp_association_put(transport->asoc); + + call_rcu(&transport->rcu, sctp_transport_destroy_rcu); } /* Start T3_rtx timer if it is not already running and update the heartbeat diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 74f6a704e374..ecbc4e3d83ad 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1660,6 +1660,10 @@ call_connect(struct rpc_task *task) task->tk_action = call_connect_status; if (task->tk_status < 0) return; + if (task->tk_flags & RPC_TASK_NOCONNECT) { + rpc_exit(task, -ENOTCONN); + return; + } xprt_connect(task); } } diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h index 74d948f5d5a1..779742cfc1ff 100644 --- a/net/sunrpc/netns.h +++ b/net/sunrpc/netns.h @@ -23,6 +23,7 @@ struct sunrpc_net { struct rpc_clnt *rpcb_local_clnt4; spinlock_t rpcb_clnt_lock; unsigned int rpcb_users; + unsigned int rpcb_is_af_local : 1; struct mutex gssp_lock; wait_queue_head_t gssp_wq; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 3df764dc330c..1891a1022c17 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -204,13 +204,15 @@ void rpcb_put_local(struct net *net) } static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, - struct rpc_clnt *clnt4) + struct rpc_clnt *clnt4, + bool is_af_local) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); /* Protected by rpcb_create_local_mutex */ sn->rpcb_local_clnt = clnt; sn->rpcb_local_clnt4 = clnt4; + sn->rpcb_is_af_local = is_af_local ? 1 : 0; smp_wmb(); sn->rpcb_users = 1; dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " @@ -238,6 +240,14 @@ static int rpcb_create_local_unix(struct net *net) .program = &rpcb_program, .version = RPCBVERS_2, .authflavor = RPC_AUTH_NULL, + /* + * We turn off the idle timeout to prevent the kernel + * from automatically disconnecting the socket. + * Otherwise, we'd have to cache the mount namespace + * of the caller and somehow pass that to the socket + * reconnect code. + */ + .flags = RPC_CLNT_CREATE_NO_IDLE_TIMEOUT, }; struct rpc_clnt *clnt, *clnt4; int result = 0; @@ -263,7 +273,7 @@ static int rpcb_create_local_unix(struct net *net) clnt4 = NULL; } - rpcb_set_local(net, clnt, clnt4); + rpcb_set_local(net, clnt, clnt4, true); out: return result; @@ -315,7 +325,7 @@ static int rpcb_create_local_net(struct net *net) clnt4 = NULL; } - rpcb_set_local(net, clnt, clnt4); + rpcb_set_local(net, clnt, clnt4, false); out: return result; @@ -376,13 +386,16 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname, return rpc_create(&args); } -static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg) +static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, struct rpc_message *msg, bool is_set) { - int result, error = 0; + int flags = RPC_TASK_NOCONNECT; + int error, result = 0; + if (is_set || !sn->rpcb_is_af_local) + flags = RPC_TASK_SOFTCONN; msg->rpc_resp = &result; - error = rpc_call_sync(clnt, msg, RPC_TASK_SOFTCONN); + error = rpc_call_sync(clnt, msg, flags); if (error < 0) { dprintk("RPC: failed to contact local rpcbind " "server (errno %d).\n", -error); @@ -439,16 +452,19 @@ int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, unsigned short .rpc_argp = &map, }; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + bool is_set = false; dprintk("RPC: %sregistering (%u, %u, %d, %u) with local " "rpcbind\n", (port ? "" : "un"), prog, vers, prot, port); msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET]; + is_set = true; + } - return rpcb_register_call(sn->rpcb_local_clnt, &msg); + return rpcb_register_call(sn, sn->rpcb_local_clnt, &msg, is_set); } /* @@ -461,6 +477,7 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin->sin_port); + bool is_set = false; int result; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); @@ -471,10 +488,12 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, map->r_addr, map->r_netid); msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + is_set = true; + } - result = rpcb_register_call(sn->rpcb_local_clnt4, msg); + result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set); kfree(map->r_addr); return result; } @@ -489,6 +508,7 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin6->sin6_port); + bool is_set = false; int result; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); @@ -499,10 +519,12 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, map->r_addr, map->r_netid); msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + is_set = true; + } - result = rpcb_register_call(sn->rpcb_local_clnt4, msg); + result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set); kfree(map->r_addr); return result; } @@ -519,7 +541,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn, map->r_addr = ""; msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - return rpcb_register_call(sn->rpcb_local_clnt4, msg); + return rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, false); } /** diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index cb29ef7ba2f0..609c30c80816 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -460,6 +460,7 @@ static void bearer_disable(struct tipc_bearer *b_ptr) { struct tipc_link *l_ptr; struct tipc_link *temp_l_ptr; + struct tipc_link_req *temp_req; pr_info("Disabling bearer <%s>\n", b_ptr->name); spin_lock_bh(&b_ptr->lock); @@ -468,9 +469,13 @@ static void bearer_disable(struct tipc_bearer *b_ptr) list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { tipc_link_delete(l_ptr); } - if (b_ptr->link_req) - tipc_disc_delete(b_ptr->link_req); + temp_req = b_ptr->link_req; + b_ptr->link_req = NULL; spin_unlock_bh(&b_ptr->lock); + + if (temp_req) + tipc_disc_delete(temp_req); + memset(b_ptr, 0, sizeof(struct tipc_bearer)); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 57896eee1c25..545c08b8a1d4 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -346,7 +346,7 @@ void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)) for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) { struct vsock_sock *vsk; list_for_each_entry(vsk, &vsock_connected_table[i], - connected_table); + connected_table) fn(sk_vsock(vsk)); } |